High-Stakes Personalization: Rethinking LLM Customization for Individual Investor Decision-Making

TL;DR

This paper examines the challenges of customizing large language models for individual investors, highlighting limitations in current methods due to the complex, evolving nature of financial decision-making.

Contribution

The authors identify key limitations in standard LLM personalization for investors and propose architectural solutions based on their deployed AI-augmented portfolio management system.

Findings

Investor behavior patterns are temporally evolving and self-contradictory.

Maintaining coherent investment rationale over time is challenging for stateless architectures.

Personalization quality cannot be evaluated against fixed labels due to stochastic outcomes.

Abstract

Personalized LLM systems have advanced rapidly, yet most operate in domains where user preferences are stable and ground truth is either absent or subjective. We argue that individual investor decision-making presents a uniquely challenging domain for LLM personalization - one that exposes fundamental limitations in current customization paradigms. Drawing on our system, built and deployed for AI-augmented portfolio management, we identify four axes along which individual investing exposes fundamental limitations in standard LLM customization: (1) behavioral memory complexity, where investor patterns are temporally evolving, self-contradictory, and financially consequential; (2) thesis consistency under drift, where maintaining coherent investment rationale over weeks or months strains stateless and session-bounded architectures; (3) style-signal tension, where the system must simultaneously respect personal investment philosophy and surface objective evidence that may contradict it; and (4) alignment without ground truth, where personalization quality cannot be evaluated against a fixed label set because outcomes are stochastic and delayed. We describe the architectural responses that emerged from building the system and propose open research directions for personalized NLP in high-stakes, temporally extended decision domains.